{"ID":2868466,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.16736","arxiv_id":"2509.16736","title":"Towards Transparent and Incentive-Compatible Collaboration in Decentralized LLM Multi-Agent Systems: A Blockchain-Driven Approach","abstract":"Large Language Models (LLMs) have enabled the emergence of autonomous agents capable of complex reasoning, planning, and interaction. However, coordinating such agents at scale remains a fundamental challenge, particularly in decentralized environments where communication lacks transparency and agent behavior cannot be shaped through centralized incentives. We propose a blockchain-based framework that enables transparent agent registration, verifiable task allocation, and dynamic reputation tracking through smart contracts. The core of our design lies in two mechanisms: a matching score-based task allocation protocol that evaluates agents by reputation, capability match, and workload; and a behavior-shaping incentive mechanism that adjusts agent behavior via feedback on performance and reward. Our implementation integrates GPT-4 agents with Solidity contracts and demonstrates, through 50-round simulations, strong task success rates, stable utility distribution, and emergent agent specialization. The results underscore the potential for trustworthy, incentive-compatible multi-agent coordination in open environments.","short_abstract":"Large Language Models (LLMs) have enabled the emergence of autonomous agents capable of complex reasoning, planning, and interaction. However, coordinating such agents at scale remains a fundamental challenge, particularly in decentralized environments where communication lacks transparency and agent behavior cannot be...","url_abs":"https://arxiv.org/abs/2509.16736","url_pdf":"https://arxiv.org/pdf/2509.16736v1","authors":"[\"Minfeng Qi\",\"Tianqing Zhu\",\"Lefeng Zhang\",\"Ningran Li\",\"Wanlei Zhou\"]","published":"2025-09-20T16:00:24Z","proceeding":"cs.MA","tasks":"[\"cs.MA\",\"cs.CR\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}